Senior LLM Engineer for Advanced Models

Join our team as a Senior LLM Research Engineer focused on developing and optimizing advanced language models. Work in challenging domains, implementing innovative data generation and evaluation strategies.
In this senior role, you will lead post-training workflows such as supervised fine-tuning and reinforcement learning. Combine your research expertise with engineering skills to handle unstructured data and create high-quality datasets. Your contributions will focus on optimization issues and model alignment to enhance model performance.

Key Responsibilities:

• Lead post-training workflows, including SFT and RL-based training

• Design robust evaluation frameworks and regression testing suites

• Create high-quality datasets from unstructured corpora

• Train and optimize models on distributed GPU infrastructure

• Improve inference efficiency through performance tuning
Requirements:

• Strong Python experience with modern LLM frameworks

• Hands-on experience fine-tuning large language models

• Deep knowledge of distributed training and GPU optimization

• Rigorous evaluation and experimentation approach

• Ability to bridge research and engineering effectively
Enhance real-world applications using your skills in model optimization and evaluation as a Senior LLM Research Engineer.
#J-18808-Ljbffr